© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47808
    Prev
    Next
    INDEX
    Explanations

    transportation routes and lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æİĸ
    -0.09
    æīĢåľ¨çļĦ
    -0.09
    å¹´å¤ľ
    -0.09
    пиÑģ
    -0.09
    è§ģåĪ°
    -0.08
    åļ
    -0.08
    åĢij
    -0.08
    è´°
    -0.08
    çĬģ
    -0.08
    strup
    -0.08
    POSITIVE LOGITS
    è¿ĻæĿ¡
    0.14
    干线
    0.12
    ä¸Ĭæľī
    0.10
    贯穿
    0.10
    ä¸ĢæĿ¡
    0.09
    沿线
    0.09
    éĢļéģĵ
    0.09
    çļĦä¸Ģéĥ¨åĪĨ
    0.09
    æĪij们çİ°åľ¨
    0.09
    éģĵ
    0.08
    Activations Density 0.174%

    No Known Activations